Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    key terms related to promises and commitments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    emarks
    -0.15
    ActionCreators
    -0.15
    abay
    -0.14
    ollen
    -0.14
    óg
    -0.14
    µ¬
    -0.14
    ailable
    -0.14
    reten
    -0.14
    èİ
    -0.13
    afari
    -0.13
    POSITIVE LOGITS
    wen
    0.15
     consent
    0.15
     thuê
    0.14
    agram
    0.14
    sher
    0.14
     Shepherd
    0.14
    roup
    0.14
     Me
    0.13
     Pu
    0.13
    agement
    0.13
    Act Density 0.005%

    No Known Activations